"When you feel how depressingly slowly you climb, it's well to remember that Things Take Time"                                                                                                                -Piet Hein

"When you get the chance to sit it out or dance,  I hope you dance"

                                                -Mark D. Sanders & Tia Sillers

Email: sridas [at] umich[dot]edu

Office address: Computer and Information Science Department

4901 Evergreen Road, 

 Dearborn, MI  48128

CV


I am currently a tenure-track Assistant Professor in the Computer & Information Sciences department at University of Michigan-Dearborn.  Prior to that, I spent three wonderful years at University of Alberta working with Prof.  Matt Taylor as part of the Intelligent Robot Learning Lab (IRL lab) . I earned my PhD in Computer Science from The University of Texas at Dallas under the supervision of Prof. Sriraam Natarajan . I was part of the StaRLing lab @ UTD .

My research interest spans across building sample-efficient models like Active Learning & Cost-sensitive learning to various decision making tasks like Reinforcement Learning, Inverse RL, Imitation learning  etc in structured domains.  I am also interested in leveraging human guidance to guide the sample-efficient and decision making models. Currently, I am interested in using human advice of different modalities and teacher-student framework to guide Reinforcement learning agents towards optimal behaviour more efficiently. 

News:

Services: